image/svg+xml
Sukhbaatar Batchuluun
Supervisor: Koichiro Shiomori
Interdisciplinary Graduate School of Agriculture and Engineering, University of Miyazaki
宮崎大学
University of Miyazaki
Preparation of polystyrene microcapsules containing water droplets by solvent
evaporation method and their structural distribution analysis by machine learning
1.Introduction
2.Methods
3.Result and discusions
4.Conclusion
- Monocore, multicore, and other aggregated structures were observed on prepared microcapsules.
- The structures were automatically detected by the Hough transformation and were classified by SVM.
- The structural distribution of the microcapsules prepared at a high weight ratio of solid to the organic phase and a lower ratio of that were analyzed
based on classification results.
- The monocore structure was dominant at the high ratio in the preparation conditions and otherwise, the multicore was dominant.
Microcapsule
?
Machine
Learning
Further work
Microcapsule
Concrete
Self sealing
4em05
4em04
0.050.100.300.50
0
25
50
75
100
125
0
25
50
75
100
125
Log(Diameter)
Count
Microcapsule structure
Monocore
Multicore
Others
S:O=2
S:O=3
4em05
4em04
0.050.100.300.50
0
25
50
75
100
125
0
25
50
75
100
125
Log(Diameter)
Count
Microcapsule structure
Monocore
Multicore
Others
81%
77%
Classifier
kNN
kNN
kNN
kNN
kNN
kNN
SVM
SVM
SVM
SVM
SVM
SVM
Color
binary
binary
gray
gray
binary
binary
binary
binary
gray
gray
binary
binary
Shape
circle
rectangle
circle
rectangle
uniform-Histogram
dense-Histogram
circle
rectangle
circle
rectangle
uniform-Histogram
dense-Histogram
Accuracy, %
80.83
64.27
82.57
59.91
40.96
69.72
71.24
51.85
83.01
45.32
55.77
65.36
Table 1.
Accuracy of the proposed feature extraction techniques.
Figure 2. Microcapsule structure.
S-SEM,
D-digital microscopy,
0-Multicore, (Class 1)
1-Monocore, (Class 2)
2-Others aggregates (Class 3)
1
Face
Full poster
Title
Key1
Key2
Key3
Intro1
Intro2
Intro3
Intro4
Intro5
Result1
Result2
Result3
Result4
Conclusion
Further work